Beyond "Just Wrappers": Inside the architecture of Box Extract
A look under the hood at how Box Extract's agentic AI architecture handles the hard parts of production document processing.
OCR-powered metadata extraction with Box AI and MCP
Box AI now uses OCR to extract structured metadata directly from image files, eliminating PDF conversion and simplifying document workflows.
Rui Barbosa, Senior Developer Advocate at Box .
Building your first Google ADK + Box agent
Learn how to create an AI agent that leverages Box’s platform and native AI to search, read, and analyze your Box content using Google’s Agent Development Kit.
Rui Barbosa, Senior Developer Advocate at Box .
Box enables the agentic enterprise with support for OpenAI's new AgentKit
Today at OpenAI DevDay, OpenAI launched AgentKit, a new suite of tools designed to accelerate the development of sophisticated AI agents. AgentKit includes Agent Builder, a low-code platform for creating agentic workflows, and Evals, a tool for rigorously testing and evaluating agent performance. At Box, we believe the future of work is agentic, and we are excited to announce our support for AgentKit, enabling developers and enterprises to build and reliably deploy powerful, content-aware AI agents grounded in their own secure business data.
Sally Li, Senior Product Marketing Manager at Box .
Create RAG-powered apps with Box loader for LangChain.js
Learn how Box’s new langchainjs-box loader lets you seamlessly bring Box files and Markdown representations into LangChain.js to build powerful RAG-powered AI applications.
Olga Stefaniuk, Developer Advocate at Box .
Latest in Box Platform
Build AI Apps with MCP Servers: Working with Box Files
Join a short online course, built in partnership with Deeplearning.ai, and taught by Ben Kus, Box CTO. By the end of this workshop, you’ll know how to build an AI application and AI agents that use the MCP server to process Box content securely, without manual downloads, and that support several file types and scale better with the number of files.
Google Gemini 3 Pro + Box AI: True Enterprise Reasoning for Real Workflows
See how to build a contract-analysis workflow using Google Gemini 3 Pro and the Box AI API.This demo walks through a Python script that extracts structured metadata from a long contract and then evaluates that contract against a library of internal reference documents stored securely in Box.
Visit Box AI Developer Zone
Box AI Developer Zone features interactive demos, sample code, and tools for building AI agents and intelligent workflows. Explore use cases, get hands-on experience with Box AI API, and build agents with Box AI Studio.
Developer stories
Introducing Box Extract: Get actionable data from enterprise content at scale
Box Extract is now available, bringing AI-powered data extraction that automatically turns unstructured content into actionable, structured metadata at enterprise scale.
Building a reusable metadata extraction Agent Skill with Box MCP and Box AI
Automate metadata extraction at scale using Box AI, MCP, and reusable Agent Skills.
How AI document extraction is changing the game
Learn how generative AI converts raw information into actionable data and why agentic document extraction is changing the game for enterprises.
Year in review: How Box Developer Relations helped you build with AI in 2025
A look back at how Box DevRel helped developers build with AI in 2025.
Learn practical AI skills and prove your expertise with Box Certified AI Professional
Level up your teams with the new, free Box AI Professional certification. Gain practical, hands‑on training to build secure, real‑world AI skills directly inside Box.
Box launches new AI-First developer documentation site
Box’s new AI-first developer docs hub features intelligent search, chat, IDE integration, and an interactive API playground to help you ship faster.
Using Box MCP server with Google ADK agent
It only takes eight lines of code to connect Google's ADK to Box
Box Community MCP tools — Finally, proper folder management!
New MCP tools in Box finally give you full programmatic control over folders. Create, organize, audit, and clean up your content at scale without ever touching the UI.
No-code app builders: A practical guide
Discover how no-code apps simplify work, connect siloed data, and empower teams to build secure, intelligent workflows at scale.
Create RAG-powered apps with Box loader for LangChain.js
Learn how Box’s new langchainjs-box loader lets you seamlessly bring Box files and Markdown representations into LangChain.js to build powerful RAG-powered AI applications.
OCR-powered metadata extraction with Box AI and MCP
Box AI now uses OCR to extract structured metadata directly from image files, eliminating PDF conversion and simplifying document workflows.